Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2766 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0355. Min Act: -0.0004

Data Index: 745659 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0341. Min Act: -0.0004

Data Index: 1206082 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0338. Min Act: -0.0004

Data Index: 1187759 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0339. Min Act: -0.0004

Data Index: 1176892 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0327. Min Act: -0.0004

Data Index: 524938 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0325. Min Act: -0.0004

Data Index: 832223 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0342. Min Act: -0.0004

Data Index: 172760 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0332. Min Act: -0.0004

Data Index: 1314236 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0336. Min Act: -0.0004

Data Index: 626058 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0317. Min Act: -0.0004

Data Index: 240340 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1115551 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0004

Data Index: 328741 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0004

Data Index: 1345512 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0328. Min Act: -0.0004

Data Index: 95641 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0315. Min Act: -0.0004

Data Index: 821028 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0336. Min Act: -0.0004

Data Index: 1012939 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1209145 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0307. Min Act: -0.0004

Data Index: 1575112 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0004

Data Index: 325937 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1134768 (C4 (Web Text))

Max Activating Token Index: 196